Search results with tag "Unsupervised adaptation"
Adversarial Discriminative Domain Adaptation
openaccess.thecvf.comdomain adaptation, as long as the latent feature space is domain invariant, and propose a discriminative approach. 3. Generalized adversarial adaptation We present a general framework for adversarial unsuper-vised adaptation methods. In unsupervised adaptation, we assume access to source images Xs and labels Ys drawn
PSD: Principled Synthetic-to-Real Dehazing Guided by ...
openaccess.thecvf.com2.2. Unsupervised Domain Adaptation Unsupervised domain adaptation aims to tackle domain shift between source and target domains, while images in the target domain are unlabeled. One major idea is to in-duce alignment between the source and target domains in feature space by optimizing for some measurements of dis-tributional discrepancy [23 ...
Deep Domain Confusion: Maximizing for Domain Invariance
arxiv.orgcan be trained for supervised adaptation, when there is a small amount of target labels available, or unsupervised adaptation, when no target labels are available. We intro-duce domain invariance through domain confusion guided selection of the depth and width of the adaptation layer, as well as an additional domain loss term during fine-tuning